search for: getoperandlatency

Hi llvm-dev, I wonder why there is an extra cycle for getOperandLatency. It doesn't seem intuitive. UseCycle = DefCycle - UseCycle + 1; When I read the comments in TargetItinerary.td, it said OperandCycles are optional "cycle counts". They specify the cycle after instruction issue the values which correspond to specific operand indices are defi...

We'd like to be able to vary the latency of our load instructions based on what address space is being loaded from. I was thinking I could do this by overriding getOperandLatency in our target, but I'm wondering if the addrspace info is available when instructions are scheduled? For example, I have this in our llvm IR: %0 = load i32 addrspace(4)* @answer, align 4 store i32 %0, i32* @xint, align 4 %1 = load i32 addrspace(2)* @seven, align 4 store i32 %1, i32* %...

...t; ../../lib/libLLVMTarget.so: error: undefined reference to > 'llvm::TargetInstrInfo::hasLowDefLatency(llvm::InstrItineraryData > const*, llvm::MachineInstr const*, unsigned int) const' > ../../lib/libLLVMTarget.so: error: undefined reference to > 'llvm::TargetInstrInfo::getOperandLatency(llvm::InstrItineraryData > const*, llvm::MachineInstr const*, unsigned int, llvm::MachineInstr > const*, unsigned int) const' > clang-3: error: linker command failed with exit code 1 (use -v to see > invocation) > make[2]: *** [bin/opt] Error 1 > make[1]: *** [tools/opt/CMa...

It it possible to specify an instruction latency in the itinerary through a command line option? We have several options for a hardware divider which have different latencies and it would be nice if I could specify it through a compiler option rather than changing the value in the code and recompiling llvm every time? Any help is appreciated. -- Rail Shafigulin Software Engineer Esencia

...st' >> ../../lib/libLLVMTarget.so: error: undefined reference to 'llvm::TargetInstrInfo::hasLowDefLatency(llvm::InstrItineraryData const*, llvm::MachineInstr const*, unsigned int) const' >> ../../lib/libLLVMTarget.so: error: undefined reference to 'llvm::TargetInstrInfo::getOperandLatency(llvm::InstrItineraryData const*, llvm::MachineInstr const*, unsigned int, llvm::MachineInstr const*, unsigned int) const' >> clang-3: error: linker command failed with exit code 1 (use -v to see invocation) >> make[2]: *** [bin/opt] Error 1 >> make[1]: *** [tools/opt/CMakeFile...

...et HighLatency = 10; } If it really helps, you could redeclare defaultDefLatency as a virtual hook and override it. (2) The "old" style of pipeline itineraries. This is closest to the old behavior. If an itinerary is defined, you get to override two hooks: virtual int TargetInstrInfo::getOperandLatency(const InstrItineraryData *ItinData, const MachineInstr *DefMI, unsigned DefIdx, const MachineInstr *UseMI, unsigned UseIdx) const; virtual unsigned TargetIns...